Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.1924. Min Act: -0.1700
Data Index: 2410967 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.1612. Min Act: -0.1700
Data Index: 8733980 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.1299. Min Act: -0.1700
Data Index: 6148971 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0987. Min Act: -0.1700
Data Index: 1271615 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0987. Min Act: -0.1700
Data Index: 7897646 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0674. Min Act: -0.1700
Data Index: 8367032 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0674. Min Act: -0.1700
Data Index: 419089 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0362. Min Act: -0.1700
Data Index: 1881056 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0362. Min Act: -0.1700
Data Index: 8789840 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0362. Min Act: -0.1700
Data Index: 4378063 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0362. Min Act: -0.1700
Data Index: 6925863 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0049. Min Act: -0.1700
Data Index: 7201463 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1924. Min Range: -5.1924
Max Act: 5.0049. Min Act: -0.1700
Data Index: 6677105 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1924. Min Range: -5.1924
Max Act: 4.9424. Min Act: -0.1700
Data Index: 945301 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1924. Min Range: -5.1924
Max Act: 4.9737. Min Act: -0.1700
Data Index: 8354614 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1924. Min Range: -5.1924
Max Act: 4.9737. Min Act: -0.1700
Data Index: 1565382 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1924. Min Range: -5.1924
Max Act: 4.9737. Min Act: -0.1700
Data Index: 5641091 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1924. Min Range: -5.1924
Max Act: 4.9737. Min Act: -0.1700
Data Index: 2891279 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1924. Min Range: -5.1924
Max Act: 4.9737. Min Act: -0.1700
Data Index: 5639248 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1924. Min Range: -5.1924
Max Act: 4.9737. Min Act: -0.1700
Data Index: 3592555 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19